© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20382
    Prev
    Next
    INDEX
    Explanations

    references to actions or situations involving saving lives or money

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of saving lives and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.64
    kt
    -0.63
    interstitial
    -0.62
     sclerosis
    -0.61
     Remastered
    -0.60
    naire
    -0.60
    secution
    -0.60
    Mand
    -0.59
    Fact
    -0.59
    oun
    -0.58
    POSITIVE LOGITS
     lives
    0.93
     Lives
    0.85
     souls
    0.81
    Save
    0.78
    anza
    0.68
    hyde
    0.66
    Instance
    0.66
    ters
    0.65
     stranded
    0.65
    éĹĺ
    0.65
    Activations Density 0.032%

    No Known Activations